{"total":138,"rows":[{"id":"2402.16801","title":"Craftax: A Lightning-Fast Benchmark for Open-Ended Reinforcement Learning","created":"2024-02-26","cited_by_count":88,"area":"deeprl"},{"id":"2401.08898","title":"Bridging State and History Representations: Understanding Self-Predictive RL","created":"2024-01-17","cited_by_count":54,"area":"deeprl"},{"id":"2407.17032","title":"Gymnasium: A Standard Interface for Reinforcement Learning Environments","created":"2024-07-24","cited_by_count":46,"area":"deeprl"},{"id":"2408.15099","title":"No Regrets: Investigating and Improving Regret Approximations for Curriculum Discovery","created":"2024-08-27","cited_by_count":31,"area":"deeprl"},{"id":"2401.11237","title":"Closing the Gap between TD Learning and Supervised Learning -- A Generalisation Point of View","created":"2024-01-20","cited_by_count":27,"area":"deeprl"},{"id":"2402.05828","title":"Discovering Temporally-Aware Reinforcement Learning Algorithms","created":"2024-02-08","cited_by_count":18,"area":"deeprl"},{"id":"2407.19396","title":"NAVIX: Scaling MiniGrid Environments with JAX","created":"2024-07-28","cited_by_count":18,"area":"deeprl"},{"id":"2506.21872","title":"A Survey of Continual Reinforcement Learning","created":"2025-06-27","cited_by_count":18,"area":"deeprl"},{"id":"2402.03046","title":"Open RL Benchmark: Comprehensive Tracked Experiments for Reinforcement Learning","created":"2024-02-05","cited_by_count":17,"area":"deeprl"},{"id":"2501.15418","title":"Episodic Novelty Through Temporal Distance","created":"2025-01-26","cited_by_count":16,"area":"deeprl"},{"id":"2411.11188","title":"AMAGO-2: Breaking the Multi-Task Barrier in Meta-Reinforcement Learning with Transformers","created":"2024-11-17","cited_by_count":15,"area":"deeprl"},{"id":"2406.08973","title":"XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning","created":"2024-06-13","cited_by_count":14,"area":"deeprl"},{"id":"2407.07082","title":"Can Learned Optimization Make Reinforcement Learning Less Difficult?","created":"2024-07-09","cited_by_count":14,"area":"deeprl"},{"id":"2406.00120","title":"Reward Machines for Deep RL in Noisy and Uncertain Environments","created":"2024-05-31","cited_by_count":11,"area":"deeprl"},{"id":"2406.17949","title":"The Overcooked Generalisation Challenge: Evaluating Cooperation with Novel Partners in Unknown Environments Using Unsupervised Environment Design","created":"2024-06-25","cited_by_count":11,"area":"deeprl"},{"id":"2505.19281","title":"A Snapshot of Influence: A Local Data Attribution Framework for Online Reinforcement Learning","created":"2025-05-25","cited_by_count":11,"area":"deeprl"},{"id":"2403.13765","title":"Towards Principled Representation Learning from Videos for Reinforcement Learning","created":"2024-03-20","cited_by_count":10,"area":"deeprl"},{"id":"2405.19548","title":"RLeXplore: Accelerating Research in Intrinsically-Motivated Reinforcement Learning","created":"2024-05-29","cited_by_count":10,"area":"deeprl"},{"id":"2410.22133","title":"Learning Successor Features the Simple Way","created":"2024-10-29","cited_by_count":10,"area":"deeprl"},{"id":"2505.20659","title":"An Optimisation Framework for Unsupervised Environment Design","created":"2025-05-27","cited_by_count":10,"area":"deeprl"},{"id":"2409.15703","title":"Agent-state based policies in POMDPs: Beyond belief-state MDPs","created":"2024-09-24","cited_by_count":9,"area":"deeprl"},{"id":"2503.15200","title":"Partially Observable Reinforcement Learning with Memory Traces","created":"2025-03-19","cited_by_count":9,"area":"deeprl"},{"id":"2501.11533","title":"The impact of intrinsic rewards on exploration in Reinforcement Learning","created":"2025-01-20","cited_by_count":8,"area":"deeprl"},{"id":"2503.00799","title":"On Generalization Across Environments In Multi-Objective Reinforcement Learning","created":"2025-03-02","cited_by_count":8,"area":"deeprl"},{"id":"2402.05284","title":"Analyzing Adversarial Inputs in Deep Reinforcement Learning","created":"2024-02-07","cited_by_count":7,"area":"deeprl"},{"id":"2405.02481","title":"Proximal Curriculum with Task Correlations for Deep Reinforcement Learning","created":"2024-05-03","cited_by_count":7,"area":"deeprl"},{"id":"2406.02035","title":"A Unifying Framework for Action-Conditional Self-Predictive Reinforcement Learning","created":"2024-06-04","cited_by_count":7,"area":"deeprl"},{"id":"2411.10175","title":"The Surprising Ineffectiveness of Pre-Trained Visual Representations for Model-Based Reinforcement Learning","created":"2024-11-15","cited_by_count":7,"area":"deeprl"},{"id":"2503.23478","title":"Handling Delay in Real-Time Reinforcement Learning","created":"2025-03-30","cited_by_count":7,"area":"deeprl"},{"id":"2508.00046","title":"Benchmarking Partial Observability in Reinforcement Learning with a Suite of Memory-Improvable Domains","created":"2025-07-31","cited_by_count":7,"area":"deeprl"},{"id":"2401.15098","title":"Multi-granularity Knowledge Transfer for Continual Reinforcement Learning","created":"2024-01-25","cited_by_count":6,"area":"deeprl"},{"id":"2403.08955","title":"Towards Efficient Risk-Sensitive Policy Gradient: An Iteration Complexity Analysis","created":"2024-03-13","cited_by_count":6,"area":"deeprl"},{"id":"2503.08241","title":"HASARD: A Benchmark for Vision-Based Safe Reinforcement Learning in Embodied Agents","created":"2025-03-11","cited_by_count":6,"area":"deeprl"},{"id":"2407.16220","title":"ODGR: Online Dynamic Goal Recognition","created":"2024-07-23","cited_by_count":5,"area":"deeprl"},{"id":"2408.08761","title":"Mitigating Information Loss in Tree-Based Reinforcement Learning via Direct Optimization","created":"2024-08-16","cited_by_count":5,"area":"deeprl"},{"id":"2412.06531","title":"Unraveling the Complexity of Memory in RL Agents: an Approach for Classification and Evaluation","created":"2024-12-09","cited_by_count":5,"area":"deeprl"},{"id":"2505.09003","title":"Continual Reinforcement Learning via Autoencoder-Driven Task and New Environment Recognition","created":"2025-05-13","cited_by_count":5,"area":"deeprl"},{"id":"2510.14176","title":"ARM-FM: Automated Reward Machines via Foundation Models for Compositional Reinforcement Learning","created":"2025-10-16","cited_by_count":5,"area":"deeprl"},{"id":"2407.12437","title":"Variable-Agnostic Causal Exploration for Reinforcement Learning","created":"2024-07-17","cited_by_count":4,"area":"deeprl"},{"id":"2407.15168","title":"Mitigating Deep Reinforcement Learning Backdoors in the Neural Activation Space","created":"2024-07-21","cited_by_count":4,"area":"deeprl"},{"id":"2407.18143","title":"Maximum Entropy On-Policy Actor-Critic via Entropy Advantage Estimation","created":"2024-07-25","cited_by_count":4,"area":"deeprl"},{"id":"2409.05358","title":"BAMDP Shaping: a Unified Framework for Intrinsic Motivation and Reward Shaping","created":"2024-09-09","cited_by_count":4,"area":"deeprl"},{"id":"2501.03888","title":"Neural DNF-MT: A Neuro-symbolic Approach for Learning Interpretable and Editable Policies","created":"2025-01-07","cited_by_count":4,"area":"deeprl"},{"id":"2506.06981","title":"Deep RL Needs Deep Behavior Analysis: Exploring Implicit Planning by Model-Free Agents in Open-Ended Environments","created":"2025-06-08","cited_by_count":4,"area":"deeprl"},{"id":"2402.00162","title":"Behind the Myth of Exploration in Policy Gradients","created":"2024-01-31","cited_by_count":3,"area":"deeprl"},{"id":"2404.02235","title":"Is Exploration All You Need? Effective Exploration Characteristics for Transfer in Reinforcement Learning","created":"2024-04-02","cited_by_count":3,"area":"deeprl"},{"id":"2411.06174","title":"State Chrono Representation for Enhancing Generalization in Reinforcement Learning","created":"2024-11-09","cited_by_count":3,"area":"deeprl"},{"id":"2412.06655","title":"Off-Policy Maximum Entropy RL with Future State and Action Visitation Measures","created":"2024-12-09","cited_by_count":3,"area":"deeprl"},{"id":"2501.00913","title":"$\\beta$-DQN: Improving Deep Q-Learning By Evolving the Behavior","created":"2025-01-01","cited_by_count":3,"area":"deeprl"},{"id":"2505.11661","title":"Learning from Less: Guiding Deep Reinforcement Learning with Differentiable Symbolic Planning","created":"2025-05-16","cited_by_count":3,"area":"deeprl"},{"id":"2506.03046","title":"EDEN: Entorhinal Driven Egocentric Navigation Toward Robotic Deployment","created":"2025-06-03","cited_by_count":3,"area":"deeprl"},{"id":"2510.02484","title":"From Pixels to Factors: Learning Independently Controllable State Variables for Reinforcement Learning","created":"2025-10-02","cited_by_count":3,"area":"deeprl"},{"id":"2503.00810","title":"Minimax Optimal Reinforcement Learning with Quasi-Optimism","created":"2025-03-02","cited_by_count":2,"area":"deeprl"},{"id":"2505.17248","title":"Backdoors in DRL: Four Environments Focusing on In-distribution Triggers","created":"2025-05-22","cited_by_count":2,"area":"deeprl"},{"id":"2505.18347","title":"The Cell Must Go On: Agar.io for Continual Reinforcement Learning","created":"2025-05-23","cited_by_count":2,"area":"deeprl"},{"id":"2506.17263","title":"Memory Allocation in Resource-Constrained Reinforcement Learning","created":"2025-06-09","cited_by_count":2,"area":"deeprl"},{"id":"2508.06871","title":"Sparsity-Driven Plasticity in Multi-Task Reinforcement Learning","created":"2025-08-09","cited_by_count":2,"area":"deeprl"},{"id":"2509.25438","title":"Beyond Noisy-TVs: Noise-Robust Exploration Via Learning Progress Monitoring","created":"2025-09-29","cited_by_count":2,"area":"deeprl"},{"id":"2511.12706","title":"Beyond Fixed Tasks: Unsupervised Environment Design for Task-Level Pairs","created":"2025-11-16","cited_by_count":2,"area":"deeprl"},{"id":"2605.14304","title":"Matrix-Space Reinforcement Learning for Reusing Local Transition Geometry","created":"2026-05-14","cited_by_count":2,"area":"deeprl"},{"id":"2606.20376","title":"CRAX: Fast Safe Reinforcement Learning Benchmarking","created":"2026-06-18","cited_by_count":2,"area":"deeprl"},{"id":"2402.05187","title":"Learning mirror maps in policy mirror descent","created":"2024-02-07","cited_by_count":1,"area":"deeprl"},{"id":"2407.08250","title":"Gradient Boosting Reinforcement Learning","created":"2024-07-11","cited_by_count":1,"area":"deeprl"},{"id":"2408.10858","title":"Centralized Reward Agent for Knowledge Sharing and Transfer in Multi-Task Reinforcement Learning","created":"2024-08-20","cited_by_count":1,"area":"deeprl"},{"id":"2501.12620","title":"Adaptive Data Exploitation in Deep Reinforcement Learning","created":"2025-01-22","cited_by_count":1,"area":"deeprl"},{"id":"2501.17077","title":"Inducing, Detecting and Characterising Neural Modules: A Pipeline for Functional Interpretability in Reinforcement Learning","created":"2025-01-28","cited_by_count":1,"area":"deeprl"},{"id":"2501.18848","title":"Reinforcement Learning of Flexible Policies for Symbolic Instructions with Adjustable Mapping Specifications","created":"2025-01-31","cited_by_count":1,"area":"deeprl"},{"id":"2502.15662","title":"Automating Curriculum Learning for Reinforcement Learning using a Skill-Based Bayesian Network","created":"2025-02-21","cited_by_count":1,"area":"deeprl"},{"id":"2503.06101","title":"ULTHO: Ultra-Lightweight yet Efficient Hyperparameter Optimization in Deep Reinforcement Learning","created":"2025-03-08","cited_by_count":1,"area":"deeprl"},{"id":"2505.01979","title":"D3HRL: A Distributed Hierarchical Reinforcement Learning Approach Based on Causal Discovery and Spurious Correlation Detection","created":"2025-05-04","cited_by_count":1,"area":"deeprl"},{"id":"2505.09737","title":"General Dynamic Goal Recognition using Goal-Conditioned and Meta Reinforcement Learning","created":"2025-05-14","cited_by_count":1,"area":"deeprl"},{"id":"2505.16581","title":"How Ensembles of Distilled Policies Improve Generalisation in Reinforcement Learning","created":"2025-05-22","cited_by_count":1,"area":"deeprl"},{"id":"2506.16590","title":"Energy-Based Transfer for Reinforcement Learning","created":"2025-06-19","cited_by_count":1,"area":"deeprl"},{"id":"2506.19997","title":"TRACED: Transition-aware Regret Approximation with Co-learnability for Environment Design","created":"2025-06-24","cited_by_count":1,"area":"deeprl"},{"id":"2508.07452","title":"Stackelberg Coupling of Online Representation Learning and Reinforcement Learning","created":"2025-08-10","cited_by_count":1,"area":"deeprl"},{"id":"2601.02850","title":"Sample-Efficient Neurosymbolic Deep Reinforcement Learning","created":"2026-01-06","cited_by_count":1,"area":"deeprl"},{"id":"2601.15086","title":"Memory Retention Is Not Enough to Master Memory Tasks in Reinforcement Learning","created":"2026-01-21","cited_by_count":1,"area":"deeprl"},{"id":"2604.04808","title":"Selecting Decision-Relevant Concepts in Reinforcement Learning","created":"2026-04-06","cited_by_count":1,"area":"deeprl"},{"id":"2604.12645","title":"Contextual Multi-Task Reinforcement Learning for Autonomous Reef Monitoring","created":"2026-04-14","cited_by_count":1,"area":"deeprl"},{"id":"2604.15414","title":"Beyond Single-Model Optimization: Preserving Plasticity in Continual Reinforcement Learning","created":"2026-04-16","cited_by_count":1,"area":"deeprl"},{"id":"2604.24729","title":"SpecRLBench: A Benchmark for Generalization in Specification-Guided Reinforcement Learning","created":"2026-04-27","cited_by_count":1,"area":"deeprl"},{"id":"2607.11906","title":"In-Context Reinforcement Learning under Non-Stationarity: A Survey","created":"2026-07-01","cited_by_count":1,"area":"deeprl"},{"id":"2406.08069","title":"Explore-Go: Leveraging Exploration for Generalisation in Deep Reinforcement Learning","created":"2024-06-12","cited_by_count":0,"area":"deeprl"},{"id":"2408.00997","title":"A Safe Exploration Strategy for Model-free Task Adaptation in Safety-constrained Grid Environments","created":"2024-08-02","cited_by_count":0,"area":"deeprl"},{"id":"2408.06068","title":"Online Optimization of Curriculum Learning Schedules using Evolutionary Optimization","created":"2024-08-12","cited_by_count":0,"area":"deeprl"},{"id":"2409.13108","title":"Disentangling Recognition and Decision Regrets in Image-Based Reinforcement Learning","created":"2024-09-19","cited_by_count":0,"area":"deeprl"},{"id":"2410.11262","title":"Unveiling Options with Neural Decomposition","created":"2024-10-15","cited_by_count":0,"area":"deeprl"},{"id":"2410.19852","title":"Survival of the Fittest: Evolutionary Adaptation of Policies for Environmental Shifts","created":"2024-10-22","cited_by_count":0,"area":"deeprl"},{"id":"2411.02998","title":"Accelerating Task Generalisation with Multi-Level Skill Hierarchies","created":"2024-11-05","cited_by_count":0,"area":"deeprl"},{"id":"2411.19787","title":"CAREL: Instruction-guided reinforcement learning with cross-modal auxiliary objectives","created":"2024-11-29","cited_by_count":0,"area":"deeprl"},{"id":"2412.08920","title":"From Text to Trajectory: Exploring Complex Constraint Representation and Decomposition in Safe Reinforcement Learning","created":"2024-12-12","cited_by_count":0,"area":"deeprl"},{"id":"2501.14543","title":"Reducing Action Space for Deep Reinforcement Learning via Causal Effect Estimation","created":"2025-01-24","cited_by_count":0,"area":"deeprl"},{"id":"2503.01941","title":"Task Scheduling & Forgetting in Multi-Task Reinforcement Learning","created":"2025-03-03","cited_by_count":0,"area":"deeprl"},{"id":"2503.10318","title":"Enhance Exploration in Safe Reinforcement Learning with Contrastive Representation Learning","created":"2025-03-13","cited_by_count":0,"area":"deeprl"},{"id":"2503.14809","title":"Learning with Expert Abstractions for Efficient Multi-Task Continuous Control","created":"2025-03-19","cited_by_count":0,"area":"deeprl"},{"id":"2506.05529","title":"Avoiding Death through Fear Intrinsic Conditioning","created":"2025-06-05","cited_by_count":0,"area":"deeprl"},{"id":"2506.06891","title":"Robust In-Context Reinforcement Learning Under Reward Poisoning Attacks","created":"2025-06-07","cited_by_count":0,"area":"deeprl"},{"id":"2509.23209","title":"Context Value Informed In-Context Reinforcement Learning","created":"2025-09-27","cited_by_count":0,"area":"deeprl"},{"id":"2509.24274","title":"Adversarial Reinforcement Learning Framework for ESP Cheater Simulation","created":"2025-09-29","cited_by_count":0,"area":"deeprl"},{"id":"2511.16158","title":"MagBotSim: Physics-Based Simulation and Reinforcement Learning Environments for Magnetic Robotics","created":"2025-11-20","cited_by_count":0,"area":"deeprl"}],"next_cursor":"100"}